junrushao commented on code in PR #12991:
URL: https://github.com/apache/tvm/pull/12991#discussion_r990654110
##########
python/tvm/meta_schedule/relay_integration.py:
##########
@@ -93,8 +93,15 @@ def _normalize_params(
if isinstance(param, np.ndarray):
param = nd.array(param)
relay_params[name] = param
- if executor is not None:
+
+ if executor is None:
+ executor = relay.backend.Executor("graph")
+
+ if mod.get_attr("executor") is None:
mod = mod.with_attr("executor", executor)
+ else:
+ executor = mod.get_attr("executor")
Review Comment:
I see! This is certainly annoying that it’s engineered this way…Thanks for
your explanation!
We probably don’t need to over-engineer it for now. Let’s keep it as it is
given vm is not supported.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
